Adaptive tactile interaction transfer via digitally embroidered smart gloves

Area of Science:

• Human-Computer Interaction
• Wearable Technology
• Haptics

Background:

• Wearable human-machine interfaces are crucial for applications like healthcare and virtual reality.
• Existing interfaces often lack scalability, wearability, and unobtrusiveness.
• Seamless integration of tactile sensors and haptic actuators into textiles is needed.

Purpose of the Study:

• To develop a scalable, wearable, and unobtrusive textile-based human-machine interface for tactile information transfer.
• To create gloves capable of recording, reproducing, and transferring tactile interactions.
• To enhance the effectiveness of tactile interaction transfer through adaptive machine learning.

Main Methods:

• Utilizing digital embroidery to embed piezoresistive force sensors and vibrotactile actuators into textiles.
• Designing and fabricating customizable, scalable, and modular textile-based gloves.
• Developing a machine-learning pipeline for adaptive haptic feedback optimization based on user perception.

Main Results:

• Demonstrated a novel method for integrating tactile sensors and haptic actuators into wearable textiles.
• Successfully created gloves that can record and reproduce tactile interactions.
• Showcased adaptive tactile interaction transfer in systems for tactile occlusion, skill guidance, and robot teleoperation.

Conclusions:

• The developed textile-based interface offers a scalable and customizable solution for wearable haptics.
• Adaptive machine learning significantly improves the effectiveness of tactile feedback.
• This technology has broad potential applications in healthcare, VR/AR, and human-robot collaboration.